Recurrent Neural Network

By Liping Liu. 2018

222 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Model Architectures

Citations in the corpus

Order Matters: Sequence to sequence for sets (2015, positive): “We trained medium sized LSTMs with large amounts of regularization (see medium model from Zaremba et al. (2014)) to estimate probabilities over sequences of words.”
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (2015, methodology): “Nevertheless, for probabilistic language models word perplexity is a well-established performance metric (Bengio et al. 2003; Mikolov et al. 2010), and has been suggested for generative dialogue models previously (Pietquin and Hastie 2013).”
Efficient Neural Architecture Search via Parameter Sharing (2018, methodology): “The second phase trains θ , the parameters of the controller LSTM, for a ﬁxed number of steps, typically set to 2000 in our experiments.”
Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, background): “As a result, RNN architectures are heavily used in domains such as Natural Language Processing (Mikolov et al., 2010), machine translation (Sutskever et al., 2014), and speech recognition (Graves et al., 2013), and are also gaining popularity in time series research (Fei and Yeung, 2015; Paw lowski ”
Abstract Syntax Networks for Code Generation and Semantic Parsing (2017, methodology): “Encoder-decoder architectures, with and without attention, have been applied successfully both to sequence prediction tasks like machine translation and to tree prediction tasks like constituency parsing (Cross and Huang, 2016; Dyer et al., 2016; Vinyals et al., 2015).”
Prediction of Sea Surface Temperature Using Long Short-Term Memory (2017, background): “Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs [4].”
Antimicrobial Peptides: Classification, Design, Application and Research Progress in Multiple Fields (2020, methodology): “Computer design includes simple statistical modeling, Structureactivity relationships study (Abdel Monaim et al., 2018), neural networks (Müller et al., 2018), deep learning (Veltri et al., 2018), word embedding (Hamid and Friedberg, 2018) and machine learning.”
A taxonomy, data set, and benchmark for detecting and classifying malevolent dialogue responses (2021, methodology): “Text-RNN uses the last hidden state (Liu et al., 2016), while a text-recurrent CNN (RCNN) uses a combination of the hidden states by adding CNN-based modules on RNN outputs to capture sequential information (Lai et al., 2015).”
Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network (2016, methodology): “We use an RNN because it has shown to be state-of-the-art language modeling (Mikolov et al. 2010) and it is also ﬂexible to realize the ﬁndings from the Cmabrigde Uinervtisy effect.”